fix：selenium 驱动配置

290453ef · liyang · 8ba9b922 · 290453ef
Commit 290453ef authored Jul 20, 2023 by liyang
Show whitespace changes
Inline Side-by-side

Showing with 15 additions and 16 deletions

pc_ptt.py pc_ptt.py +15 -16

No files found.
--- a/pc_ptt.py
+++ b/pc_ptt.py
@@ -94,7 +94,22 @@ def reptile(browser=None, search_word=""):
                    # 将datetime对象转换为时间戳（以秒为单位）
                    release_time = int(date_time.timestamp())
                    # log.debug('开始判断类型')
+                    try:
+                        # 找到所有第一级标签为 `div` 的元素
+                        div_elements = soup.find_all('div')
+                        # log.debug("一级div数量：" + str(len(div_elements)))
+                        # 逐个删除这些元素
+                        for div in div_elements:
+                            div.extract()
+                        # 删除第一级span
+                        span_element = soup.find_all('span')
+                        # log.debug("一级span数量：" + str(len(span_element)))
+                        for span in span_element:
+                            span.extract()

+                    except:
+                        # log.debug("删除第一级div失败")
+                        a = 2
                    # ---------------- 判断类型 start ----------
                    # 类型
                    content_type = ""
@@ -136,22 +151,6 @@ def reptile(browser=None, search_word=""):
                    except:
                        # log.debug("查找所有的<a>标签失败")
                        a = 1
-                    try:
-                        # 找到所有第一级标签为 `div` 的元素
-                        div_elements = soup.find_all('div')
-                        # log.debug("一级div数量：" + str(len(div_elements)))
-                        # 逐个删除这些元素
-                        for div in div_elements:
-                            div.extract()
-                        # 删除第一级span
-                        span_element = soup.find_all('span')
-                        # log.debug("一级span数量：" + str(len(span_element)))
-                        for span in span_element:
-                            span.extract()
-
-                    except:
-                        # log.debug("删除第一级div失败")
-                        a = 2
                    html = soup.prettify().replace('amp;', '')
                    # ------------------ content 过滤 end--------------